Goal: Do a PCA plot using Irene’s SNPs to look for relatedness among plants. Also figure out loading (which genes contribute most)
First, need to call SNPs using all BAM files at once:
working in directory 2019/IreneSnps on whitney
first, sort bams
for f in SNPanalysis/*LT*rmdup.bam
do
newname=`basename $f .bam`_sort.bam
samtools sort -o $newname --reference SNPanalysis/Pinsaporeference1 $f
done
next, assign read groups to bams
input=""
for f in `ls *sort.bam`
do
rg=`basename $f _rmdup_sort.bam`
input="$input -b $f -r $rg -s $rg"
done
echo $input
bamaddrg $input > LT_rmdup_sort_combined.bam
samtools index LT_rmdup_sort_combined.bam
freebayes -f SNPanalysis/Pinsaporeference1 --no-indels --no-mnps --no-complex LT_rmdup_sort_combined.bam > LT.vcf &
try parallel
ulimit -n 4000
/usr/local/stow/freebayes/scripts/fasta_generate_regions.py Pinsaporeference1.fai 100000 > regions
./freebayes-parallel regions 8 -f Pinsaporeference1 --no-indels --no-mnps --no-complex LT_rmdup_sort_combined.bam > LT.vcf
(note: I edited the freebayes-parallel script so that it would work…)
Freeybayes parallel takes about 12 hours
scp whitney.plb.ucdavis.edu:2019/IreneSnps/LT.vcf.gz ../input/
library(tidyverse)
[30m── [1mAttaching packages[22m ────────────────────────────────────────────────────────────────────────────────────────────── tidyverse 1.2.1 ──[39m
[30m[32m✔[30m [34mggplot2[30m 3.0.0 [32m✔[30m [34mpurrr [30m 0.2.5
[32m✔[30m [34mtibble [30m 1.4.2 [32m✔[30m [34mdplyr [30m 0.7.6
[32m✔[30m [34mtidyr [30m 0.8.1 [32m✔[30m [34mstringr[30m 1.3.1
[32m✔[30m [34mreadr [30m 1.1.1 [32m✔[30m [34mforcats[30m 0.3.0[39m
[30m── [1mConflicts[22m ───────────────────────────────────────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
[31m✖[30m [34mdplyr[30m::[32mfilter()[30m masks [34mstats[30m::filter()
[31m✖[30m [34mdplyr[30m::[32mlag()[30m masks [34mstats[30m::lag()[39m
library(ggrepel)
get the vcf header
vcf.header <- system("zgrep '#C' ../input/LT.vcf.gz",intern = TRUE)
vcf.header
[1] "#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\tFORMAT\t38LTR\t42LTR\t42LTRR\t43LTR\t43LTRR\t49LTWR\t49LTWRR\t95LTWR\t95LTWRR\t99LTWR"
vcf.header <- vcf.header %>%
str_replace("#","") %>% #get rid of the pound sign
str_split(pattern = "\t") %>% #split on the tabs
magrittr::extract2(1)
vcf.header
[1] "CHROM" "POS" "ID" "REF" "ALT" "QUAL" "FILTER" "INFO" "FORMAT" "38LTR" "42LTR" "42LTRR" "43LTR"
[14] "43LTRR" "49LTWR" "49LTWRR" "95LTWR" "95LTWRR" "99LTWR"
get the data
snps <- read_tsv("../input/LT.vcf.gz", na = c("","NA","."),comment="#",col_names = vcf.header) %>%
select(-ID, -FILTER) # these are empty columns
Parsed with column specification:
cols(
CHROM = col_character(),
POS = col_integer(),
ID = col_character(),
REF = col_character(),
ALT = col_character(),
QUAL = col_double(),
FILTER = col_character(),
INFO = col_character(),
FORMAT = col_character(),
`38LTR` = col_character(),
`42LTR` = col_character(),
`42LTRR` = col_character(),
`43LTR` = col_character(),
`43LTRR` = col_character(),
`49LTWR` = col_character(),
`49LTWRR` = col_character(),
`95LTWR` = col_character(),
`95LTWRR` = col_character(),
`99LTWR` = col_character()
)
|======= | 6% 25 MB
|======= | 6% 26 MB
|======== | 6% 26 MB
|======== | 6% 27 MB
|======== | 6% 27 MB
|======== | 6% 27 MB
|======== | 7% 28 MB
|======== | 7% 28 MB
|======== | 7% 29 MB
|======== | 7% 29 MB
|======== | 7% 29 MB
|========= | 7% 30 MB
|========= | 7% 30 MB
|========= | 7% 30 MB
|========= | 7% 31 MB
|========= | 7% 31 MB
|========= | 8% 32 MB
|========= | 8% 32 MB
|========= | 8% 32 MB
|========== | 8% 33 MB
|========== | 8% 33 MB
|========== | 8% 34 MB
|========== | 8% 34 MB
|========== | 8% 34 MB
|========== | 8% 35 MB
|========== | 8% 35 MB
|========== | 9% 36 MB
|========== | 9% 36 MB
|=========== | 9% 36 MB
|=========== | 9% 37 MB
|=========== | 9% 37 MB
|=========== | 9% 37 MB
|=========== | 9% 38 MB
|=========== | 9% 38 MB
|=========== | 9% 39 MB
|=========== | 9% 39 MB
|=========== | 9% 39 MB
|============ | 10% 40 MB
|============ | 10% 40 MB
|============ | 10% 40 MB
|============ | 10% 41 MB
|============ | 10% 41 MB
|============ | 10% 42 MB
|============ | 10% 42 MB
|============ | 10% 42 MB
|============= | 10% 43 MB
|============= | 10% 43 MB
|============= | 11% 44 MB
|============= | 11% 44 MB
|============= | 11% 44 MB
|============= | 11% 45 MB
|============= | 11% 45 MB
|============= | 11% 46 MB
|============= | 11% 46 MB
|============== | 11% 46 MB
|============== | 11% 47 MB
|============== | 11% 47 MB
|============== | 12% 47 MB
|============== | 12% 48 MB
|============== | 12% 48 MB
|============== | 12% 49 MB
|============== | 12% 49 MB
|=============== | 12% 49 MB
|=============== | 12% 50 MB
|=============== | 12% 50 MB
|=============== | 12% 51 MB
|=============== | 12% 51 MB
|=============== | 12% 51 MB
|=============== | 13% 52 MB
|=============== | 13% 52 MB
|=============== | 13% 53 MB
|================ | 13% 53 MB
|================ | 13% 53 MB
|================ | 13% 54 MB
|================ | 13% 54 MB
|================ | 13% 54 MB
|================ | 13% 55 MB
|================ | 13% 55 MB
|================ | 14% 56 MB
|================ | 14% 56 MB
|================= | 14% 56 MB
|================= | 14% 57 MB
|================= | 14% 57 MB
|================= | 14% 57 MB
|================= | 14% 58 MB
|================= | 14% 58 MB
|================= | 14% 59 MB
|================= | 14% 59 MB
|================== | 15% 59 MB
|================== | 15% 60 MB
|================== | 15% 60 MB
|================== | 15% 61 MB
|================== | 15% 61 MB
|================== | 15% 61 MB
|================== | 15% 62 MB
|================== | 15% 62 MB
|================== | 15% 63 MB
|=================== | 15% 63 MB
|=================== | 15% 63 MB
|=================== | 16% 64 MB
|=================== | 16% 64 MB
|=================== | 16% 64 MB
|=================== | 16% 65 MB
|=================== | 16% 65 MB
|=================== | 16% 66 MB
|=================== | 16% 66 MB
|==================== | 16% 66 MB
|==================== | 16% 67 MB
|==================== | 16% 67 MB
|==================== | 17% 68 MB
|==================== | 17% 68 MB
|==================== | 17% 68 MB
|==================== | 17% 69 MB
|==================== | 17% 69 MB
|===================== | 17% 69 MB
|===================== | 17% 70 MB
|===================== | 17% 70 MB
|===================== | 17% 71 MB
|===================== | 17% 71 MB
|===================== | 18% 71 MB
|===================== | 18% 72 MB
|===================== | 18% 72 MB
|===================== | 18% 73 MB
|====================== | 18% 73 MB
|====================== | 18% 73 MB
|====================== | 18% 74 MB
|====================== | 18% 74 MB
|====================== | 18% 74 MB
|====================== | 18% 75 MB
|====================== | 18% 75 MB
|====================== | 19% 76 MB
|======================= | 19% 76 MB
|======================= | 19% 76 MB
|======================= | 19% 77 MB
|======================= | 19% 77 MB
|======================= | 19% 78 MB
|======================= | 19% 78 MB
|======================= | 19% 78 MB
|======================= | 19% 79 MB
|======================= | 19% 79 MB
|======================== | 20% 79 MB
|======================== | 20% 80 MB
|======================== | 20% 80 MB
|======================== | 20% 81 MB
|======================== | 20% 81 MB
|======================== | 20% 81 MB
|======================== | 20% 82 MB
|======================== | 20% 82 MB
|======================== | 20% 83 MB
|========================= | 20% 83 MB
|========================= | 21% 83 MB
|========================= | 21% 84 MB
|========================= | 21% 84 MB
|========================= | 21% 84 MB
|========================= | 21% 85 MB
|========================= | 21% 85 MB
|========================= | 21% 86 MB
|========================= | 21% 86 MB
|========================== | 21% 86 MB
|========================== | 21% 87 MB
|========================== | 21% 87 MB
|========================== | 22% 87 MB
|========================== | 22% 88 MB
|========================== | 22% 88 MB
|========================== | 22% 89 MB
|========================== | 22% 89 MB
|=========================== | 22% 89 MB
|=========================== | 22% 90 MB
|=========================== | 22% 90 MB
|=========================== | 22% 91 MB
|=========================== | 22% 91 MB
|=========================== | 23% 91 MB
|=========================== | 23% 92 MB
|=========================== | 23% 92 MB
|=========================== | 23% 92 MB
|============================ | 23% 93 MB
|============================ | 23% 93 MB
|============================ | 23% 94 MB
|============================ | 23% 94 MB
|============================ | 23% 94 MB
|============================ | 23% 95 MB
|============================ | 23% 95 MB
|============================ | 24% 95 MB
|============================ | 24% 96 MB
|============================= | 24% 96 MB
|============================= | 24% 97 MB
|============================= | 24% 97 MB
|============================= | 24% 97 MB
|============================= | 24% 98 MB
|============================= | 24% 98 MB
|============================= | 24% 99 MB
|============================= | 24% 99 MB
|============================== | 25% 99 MB
|============================== | 25% 100 MB
|============================== | 25% 100 MB
|============================== | 25% 100 MB
|============================== | 25% 101 MB
|============================== | 25% 101 MB
|============================== | 25% 102 MB
|============================== | 25% 102 MB
|============================== | 25% 102 MB
|=============================== | 25% 103 MB
|=============================== | 25% 103 MB
|=============================== | 26% 104 MB
|=============================== | 26% 104 MB
|=============================== | 26% 104 MB
|=============================== | 26% 105 MB
|=============================== | 26% 105 MB
|=============================== | 26% 105 MB
|=============================== | 26% 106 MB
|================================ | 26% 106 MB
|================================ | 26% 107 MB
|================================ | 26% 107 MB
|================================ | 27% 107 MB
|================================ | 27% 108 MB
|================================ | 27% 108 MB
|================================ | 27% 109 MB
|================================ | 27% 109 MB
|================================= | 27% 109 MB
|================================= | 27% 110 MB
|================================= | 27% 110 MB
|================================= | 27% 110 MB
|================================= | 27% 111 MB
|================================= | 27% 111 MB
|================================= | 28% 112 MB
|================================= | 28% 112 MB
|================================= | 28% 112 MB
|================================== | 28% 113 MB
|================================== | 28% 113 MB
|================================== | 28% 114 MB
|================================== | 28% 114 MB
|================================== | 28% 114 MB
|================================== | 28% 115 MB
|================================== | 28% 115 MB
|================================== | 29% 116 MB
|=================================== | 29% 116 MB
|=================================== | 29% 116 MB
|=================================== | 29% 117 MB
|=================================== | 29% 117 MB
|=================================== | 29% 117 MB
|=================================== | 29% 118 MB
|=================================== | 29% 118 MB
|=================================== | 29% 119 MB
|=================================== | 29% 119 MB
|==================================== | 30% 119 MB
|==================================== | 30% 120 MB
|==================================== | 30% 120 MB
|==================================== | 30% 121 MB
|==================================== | 30% 121 MB
|==================================== | 30% 121 MB
|==================================== | 30% 122 MB
|==================================== | 30% 122 MB
|==================================== | 30% 122 MB
|===================================== | 30% 123 MB
|===================================== | 31% 123 MB
|===================================== | 31% 124 MB
|===================================== | 31% 124 MB
|===================================== | 31% 124 MB
|===================================== | 31% 125 MB
|===================================== | 31% 125 MB
|===================================== | 31% 126 MB
|====================================== | 31% 126 MB
|====================================== | 31% 126 MB
|====================================== | 31% 127 MB
|====================================== | 31% 127 MB
|====================================== | 32% 128 MB
|====================================== | 32% 128 MB
|====================================== | 32% 128 MB
|====================================== | 32% 129 MB
|====================================== | 32% 129 MB
|======================================= | 32% 129 MB
|======================================= | 32% 130 MB
|======================================= | 32% 130 MB
|======================================= | 32% 131 MB
|======================================= | 32% 131 MB
|======================================= | 33% 131 MB
|======================================= | 33% 132 MB
|======================================= | 33% 132 MB
|======================================== | 33% 133 MB
|======================================== | 33% 133 MB
|======================================== | 33% 133 MB
|======================================== | 33% 134 MB
|======================================== | 33% 134 MB
|======================================== | 33% 135 MB
|======================================== | 33% 135 MB
|======================================== | 34% 135 MB
|========================================= | 34% 136 MB
|========================================= | 34% 136 MB
|========================================= | 34% 137 MB
|========================================= | 34% 137 MB
|========================================= | 34% 137 MB
|========================================= | 34% 138 MB
|========================================= | 34% 138 MB
|========================================= | 34% 139 MB
|========================================= | 34% 139 MB
|========================================== | 35% 139 MB
|========================================== | 35% 140 MB
|========================================== | 35% 140 MB
|========================================== | 35% 141 MB
|========================================== | 35% 141 MB
|========================================== | 35% 141 MB
|========================================== | 35% 142 MB
|========================================== | 35% 142 MB
|========================================== | 35% 142 MB
|=========================================== | 35% 143 MB
|=========================================== | 36% 143 MB
|=========================================== | 36% 144 MB
|=========================================== | 36% 144 MB
|=========================================== | 36% 144 MB
|=========================================== | 36% 145 MB
|=========================================== | 36% 145 MB
|=========================================== | 36% 146 MB
|============================================ | 36% 146 MB
|============================================ | 36% 146 MB
|============================================ | 36% 147 MB
|============================================ | 37% 147 MB
|============================================ | 37% 148 MB
|============================================ | 37% 148 MB
|============================================ | 37% 148 MB
|============================================ | 37% 149 MB
|============================================= | 37% 149 MB
|============================================= | 37% 150 MB
|============================================= | 37% 150 MB
|============================================= | 37% 150 MB
|============================================= | 37% 151 MB
|============================================= | 37% 151 MB
|============================================= | 38% 151 MB
|============================================= | 38% 152 MB
|============================================= | 38% 152 MB
|============================================== | 38% 153 MB
|============================================== | 38% 153 MB
|============================================== | 38% 153 MB
|============================================== | 38% 154 MB
|============================================== | 38% 154 MB
|============================================== | 38% 155 MB
|============================================== | 38% 155 MB
|============================================== | 39% 155 MB
|=============================================== | 39% 156 MB
|=============================================== | 39% 156 MB
|=============================================== | 39% 157 MB
|=============================================== | 39% 157 MB
|=============================================== | 39% 157 MB
|=============================================== | 39% 158 MB
|=============================================== | 39% 158 MB
|=============================================== | 39% 159 MB
|=============================================== | 39% 159 MB
|================================================ | 40% 159 MB
|================================================ | 40% 160 MB
|================================================ | 40% 160 MB
|================================================ | 40% 160 MB
|================================================ | 40% 161 MB
|================================================ | 40% 161 MB
|================================================ | 40% 162 MB
|================================================ | 40% 162 MB
|================================================= | 40% 162 MB
|================================================= | 40% 163 MB
|================================================= | 41% 163 MB
|================================================= | 41% 164 MB
|================================================= | 41% 164 MB
|================================================= | 41% 164 MB
|================================================= | 41% 165 MB
|================================================= | 41% 165 MB
|================================================= | 41% 166 MB
|================================================== | 41% 166 MB
|================================================== | 41% 166 MB
|================================================== | 41% 167 MB
|================================================== | 42% 167 MB
|================================================== | 42% 168 MB
|================================================== | 42% 168 MB
|================================================== | 42% 168 MB
|================================================== | 42% 169 MB
|=================================================== | 42% 169 MB
|=================================================== | 42% 170 MB
|=================================================== | 42% 170 MB
|=================================================== | 42% 171 MB
|=================================================== | 42% 171 MB
|=================================================== | 43% 171 MB
|=================================================== | 43% 172 MB
|=================================================== | 43% 172 MB
|==================================================== | 43% 173 MB
|==================================================== | 43% 173 MB
|==================================================== | 43% 173 MB
|==================================================== | 43% 174 MB
|==================================================== | 43% 174 MB
|==================================================== | 43% 175 MB
|==================================================== | 44% 175 MB
|==================================================== | 44% 175 MB
|===================================================== | 44% 176 MB
|===================================================== | 44% 176 MB
|===================================================== | 44% 177 MB
|===================================================== | 44% 177 MB
|===================================================== | 44% 177 MB
|===================================================== | 44% 178 MB
|===================================================== | 44% 178 MB
|===================================================== | 44% 179 MB
|===================================================== | 44% 179 MB
|====================================================== | 45% 179 MB
|====================================================== | 45% 180 MB
|====================================================== | 45% 180 MB
|====================================================== | 45% 181 MB
|====================================================== | 45% 181 MB
|====================================================== | 45% 181 MB
|====================================================== | 45% 182 MB
|====================================================== | 45% 182 MB
|======================================================= | 45% 183 MB
|======================================================= | 46% 183 MB
|======================================================= | 46% 183 MB
|======================================================= | 46% 184 MB
|======================================================= | 46% 184 MB
|======================================================= | 46% 185 MB
|======================================================= | 46% 185 MB
|======================================================= | 46% 185 MB
|======================================================== | 46% 186 MB
|======================================================== | 46% 186 MB
|======================================================== | 46% 187 MB
|======================================================== | 46% 187 MB
|======================================================== | 47% 187 MB
|======================================================== | 47% 188 MB
|======================================================== | 47% 188 MB
|======================================================== | 47% 188 MB
|======================================================== | 47% 189 MB
|========================================================= | 47% 189 MB
|========================================================= | 47% 190 MB
|========================================================= | 47% 190 MB
|========================================================= | 47% 190 MB
|========================================================= | 47% 191 MB
|========================================================= | 48% 191 MB
|========================================================= | 48% 192 MB
|========================================================= | 48% 192 MB
|========================================================== | 48% 193 MB
|========================================================== | 48% 193 MB
|========================================================== | 48% 193 MB
|========================================================== | 48% 194 MB
|========================================================== | 48% 194 MB
|========================================================== | 48% 194 MB
|========================================================== | 48% 195 MB
|========================================================== | 49% 195 MB
|========================================================== | 49% 196 MB
|=========================================================== | 49% 196 MB
|=========================================================== | 49% 196 MB
|=========================================================== | 49% 197 MB
|=========================================================== | 49% 197 MB
|=========================================================== | 49% 198 MB
|=========================================================== | 49% 198 MB
|=========================================================== | 49% 199 MB
|=========================================================== | 49% 199 MB
|============================================================ | 50% 199 MB
|============================================================ | 50% 200 MB
|============================================================ | 50% 200 MB
|============================================================ | 50% 201 MB
|============================================================ | 50% 201 MB
|============================================================ | 50% 201 MB
|============================================================ | 50% 202 MB
|============================================================ | 50% 202 MB
|============================================================= | 50% 203 MB
|============================================================= | 50% 203 MB
|============================================================= | 51% 203 MB
|============================================================= | 51% 204 MB
|============================================================= | 51% 204 MB
|============================================================= | 51% 204 MB
|============================================================= | 51% 205 MB
|============================================================= | 51% 205 MB
|============================================================= | 51% 206 MB
|============================================================== | 51% 206 MB
|============================================================== | 51% 206 MB
|============================================================== | 51% 207 MB
|============================================================== | 52% 207 MB
|============================================================== | 52% 208 MB
|============================================================== | 52% 208 MB
|============================================================== | 52% 208 MB
|============================================================== | 52% 209 MB
|=============================================================== | 52% 209 MB
|=============================================================== | 52% 210 MB
|=============================================================== | 52% 210 MB
|=============================================================== | 52% 210 MB
|=============================================================== | 52% 211 MB
|=============================================================== | 53% 211 MB
|=============================================================== | 53% 212 MB
|=============================================================== | 53% 212 MB
|================================================================ | 53% 212 MB
|================================================================ | 53% 213 MB
|================================================================ | 53% 213 MB
|================================================================ | 53% 213 MB
|================================================================ | 53% 214 MB
|================================================================ | 53% 214 MB
|================================================================ | 53% 215 MB
|================================================================ | 54% 215 MB
|================================================================ | 54% 216 MB
|================================================================= | 54% 216 MB
|================================================================= | 54% 216 MB
|================================================================= | 54% 217 MB
|================================================================= | 54% 217 MB
|================================================================= | 54% 217 MB
|================================================================= | 54% 218 MB
|================================================================= | 54% 218 MB
|================================================================= | 54% 219 MB
|================================================================== | 55% 219 MB
|================================================================== | 55% 219 MB
|================================================================== | 55% 220 MB
|================================================================== | 55% 220 MB
|================================================================== | 55% 221 MB
|================================================================== | 55% 221 MB
|================================================================== | 55% 221 MB
|================================================================== | 55% 222 MB
|================================================================== | 55% 222 MB
|=================================================================== | 55% 223 MB
|=================================================================== | 55% 223 MB
|=================================================================== | 56% 223 MB
|=================================================================== | 56% 224 MB
|=================================================================== | 56% 224 MB
|=================================================================== | 56% 224 MB
|=================================================================== | 56% 225 MB
|=================================================================== | 56% 225 MB
|==================================================================== | 56% 226 MB
|==================================================================== | 56% 226 MB
|==================================================================== | 56% 226 MB
|==================================================================== | 56% 227 MB
|==================================================================== | 57% 227 MB
|==================================================================== | 57% 228 MB
|==================================================================== | 57% 228 MB
|==================================================================== | 57% 228 MB
|==================================================================== | 57% 229 MB
|===================================================================== | 57% 229 MB
|===================================================================== | 57% 230 MB
|===================================================================== | 57% 230 MB
|===================================================================== | 57% 230 MB
|===================================================================== | 57% 231 MB
|===================================================================== | 58% 231 MB
|===================================================================== | 58% 232 MB
|===================================================================== | 58% 232 MB
|====================================================================== | 58% 232 MB
|====================================================================== | 58% 233 MB
|====================================================================== | 58% 233 MB
|====================================================================== | 58% 233 MB
|====================================================================== | 58% 234 MB
|====================================================================== | 58% 234 MB
|====================================================================== | 58% 235 MB
|====================================================================== | 59% 235 MB
|====================================================================== | 59% 235 MB
|======================================================================= | 59% 236 MB
|======================================================================= | 59% 236 MB
|======================================================================= | 59% 237 MB
|======================================================================= | 59% 237 MB
|======================================================================= | 59% 237 MB
|======================================================================= | 59% 238 MB
|======================================================================= | 59% 238 MB
|======================================================================= | 59% 238 MB
|======================================================================= | 59% 239 MB
|======================================================================== | 60% 239 MB
|======================================================================== | 60% 240 MB
|======================================================================== | 60% 240 MB
|======================================================================== | 60% 240 MB
|======================================================================== | 60% 241 MB
|======================================================================== | 60% 241 MB
|======================================================================== | 60% 242 MB
|======================================================================== | 60% 242 MB
|========================================================================= | 60% 242 MB
|========================================================================= | 60% 243 MB
|========================================================================= | 61% 243 MB
|========================================================================= | 61% 244 MB
|========================================================================= | 61% 244 MB
|========================================================================= | 61% 244 MB
|========================================================================= | 61% 245 MB
|========================================================================= | 61% 245 MB
|========================================================================== | 61% 246 MB
|========================================================================== | 61% 246 MB
|========================================================================== | 61% 246 MB
|========================================================================== | 61% 247 MB
|========================================================================== | 62% 247 MB
|========================================================================== | 62% 248 MB
|========================================================================== | 62% 248 MB
|========================================================================== | 62% 248 MB
|========================================================================== | 62% 249 MB
|=========================================================================== | 62% 249 MB
|=========================================================================== | 62% 249 MB
|=========================================================================== | 62% 250 MB
|=========================================================================== | 62% 250 MB
|=========================================================================== | 62% 251 MB
|=========================================================================== | 63% 251 MB
|=========================================================================== | 63% 251 MB
|=========================================================================== | 63% 252 MB
|=========================================================================== | 63% 252 MB
|============================================================================ | 63% 253 MB
|============================================================================ | 63% 253 MB
|============================================================================ | 63% 253 MB
|============================================================================ | 63% 254 MB
|============================================================================ | 63% 254 MB
|============================================================================ | 63% 255 MB
|============================================================================ | 64% 255 MB
|============================================================================ | 64% 255 MB
|============================================================================= | 64% 256 MB
|============================================================================= | 64% 256 MB
|============================================================================= | 64% 256 MB
|============================================================================= | 64% 257 MB
|============================================================================= | 64% 257 MB
|============================================================================= | 64% 258 MB
|============================================================================= | 64% 258 MB
|============================================================================= | 64% 258 MB
|============================================================================= | 64% 259 MB
|============================================================================== | 65% 259 MB
|============================================================================== | 65% 260 MB
|============================================================================== | 65% 260 MB
|============================================================================== | 65% 260 MB
|============================================================================== | 65% 261 MB
|============================================================================== | 65% 261 MB
|============================================================================== | 65% 262 MB
|============================================================================== | 65% 262 MB
|=============================================================================== | 65% 262 MB
|=============================================================================== | 65% 263 MB
|=============================================================================== | 66% 263 MB
|=============================================================================== | 66% 264 MB
|=============================================================================== | 66% 264 MB
|=============================================================================== | 66% 264 MB
|=============================================================================== | 66% 265 MB
|=============================================================================== | 66% 265 MB
|================================================================================ | 66% 265 MB
|================================================================================ | 66% 266 MB
|================================================================================ | 66% 266 MB
|================================================================================ | 66% 267 MB
|================================================================================ | 67% 267 MB
|================================================================================ | 67% 267 MB
|================================================================================ | 67% 268 MB
|================================================================================ | 67% 268 MB
|================================================================================ | 67% 269 MB
|================================================================================= | 67% 269 MB
|================================================================================= | 67% 269 MB
|================================================================================= | 67% 270 MB
|================================================================================= | 67% 270 MB
|================================================================================= | 67% 271 MB
|================================================================================= | 68% 271 MB
|================================================================================= | 68% 271 MB
|================================================================================= | 68% 272 MB
|================================================================================= | 68% 272 MB
|================================================================================== | 68% 273 MB
|================================================================================== | 68% 273 MB
|================================================================================== | 68% 273 MB
|================================================================================== | 68% 274 MB
|================================================================================== | 68% 274 MB
|================================================================================== | 68% 274 MB
|================================================================================== | 69% 275 MB
|================================================================================== | 69% 275 MB
|=================================================================================== | 69% 276 MB
|=================================================================================== | 69% 276 MB
|=================================================================================== | 69% 277 MB
|=================================================================================== | 69% 277 MB
|=================================================================================== | 69% 277 MB
|=================================================================================== | 69% 278 MB
|=================================================================================== | 69% 278 MB
|=================================================================================== | 69% 279 MB
|==================================================================================== | 70% 279 MB
|==================================================================================== | 70% 279 MB
|==================================================================================== | 70% 280 MB
|==================================================================================== | 70% 280 MB
|==================================================================================== | 70% 280 MB
|==================================================================================== | 70% 281 MB
|==================================================================================== | 70% 281 MB
|==================================================================================== | 70% 282 MB
|==================================================================================== | 70% 282 MB
|===================================================================================== | 70% 282 MB
|===================================================================================== | 71% 283 MB
|===================================================================================== | 71% 283 MB
|===================================================================================== | 71% 284 MB
|===================================================================================== | 71% 284 MB
|===================================================================================== | 71% 284 MB
|===================================================================================== | 71% 285 MB
|===================================================================================== | 71% 285 MB
|====================================================================================== | 71% 285 MB
|====================================================================================== | 71% 286 MB
|====================================================================================== | 71% 286 MB
|====================================================================================== | 71% 287 MB
|====================================================================================== | 72% 287 MB
|====================================================================================== | 72% 287 MB
|====================================================================================== | 72% 288 MB
|====================================================================================== | 72% 288 MB
|====================================================================================== | 72% 289 MB
|======================================================================================= | 72% 289 MB
|======================================================================================= | 72% 289 MB
|======================================================================================= | 72% 290 MB
|======================================================================================= | 72% 290 MB
|======================================================================================= | 72% 290 MB
|======================================================================================= | 73% 291 MB
|======================================================================================= | 73% 291 MB
|======================================================================================= | 73% 292 MB
|======================================================================================= | 73% 292 MB
|======================================================================================== | 73% 292 MB
|======================================================================================== | 73% 293 MB
|======================================================================================== | 73% 293 MB
|======================================================================================== | 73% 294 MB
|======================================================================================== | 73% 294 MB
|======================================================================================== | 73% 294 MB
|======================================================================================== | 74% 295 MB
|======================================================================================== | 74% 295 MB
|========================================================================================= | 74% 296 MB
|========================================================================================= | 74% 296 MB
|========================================================================================= | 74% 296 MB
|========================================================================================= | 74% 297 MB
|========================================================================================= | 74% 297 MB
|========================================================================================= | 74% 298 MB
|========================================================================================= | 74% 298 MB
|========================================================================================= | 74% 298 MB
|========================================================================================= | 74% 299 MB
|========================================================================================== | 75% 299 MB
|========================================================================================== | 75% 299 MB
|========================================================================================== | 75% 300 MB
|========================================================================================== | 75% 300 MB
|========================================================================================== | 75% 301 MB
|========================================================================================== | 75% 301 MB
|========================================================================================== | 75% 301 MB
|========================================================================================== | 75% 302 MB
|=========================================================================================== | 75% 302 MB
|=========================================================================================== | 75% 303 MB
|=========================================================================================== | 76% 303 MB
|=========================================================================================== | 76% 303 MB
|=========================================================================================== | 76% 304 MB
|=========================================================================================== | 76% 304 MB
|=========================================================================================== | 76% 304 MB
|=========================================================================================== | 76% 305 MB
|=========================================================================================== | 76% 305 MB
|============================================================================================ | 76% 306 MB
|============================================================================================ | 76% 306 MB
|============================================================================================ | 76% 306 MB
|============================================================================================ | 77% 307 MB
|============================================================================================ | 77% 307 MB
|============================================================================================ | 77% 308 MB
|============================================================================================ | 77% 308 MB
|============================================================================================ | 77% 308 MB
|============================================================================================= | 77% 309 MB
|============================================================================================= | 77% 309 MB
|============================================================================================= | 77% 310 MB
|============================================================================================= | 77% 310 MB
|============================================================================================= | 77% 310 MB
|============================================================================================= | 78% 311 MB
|============================================================================================= | 78% 311 MB
|============================================================================================= | 78% 312 MB
|============================================================================================= | 78% 312 MB
|============================================================================================== | 78% 312 MB
|============================================================================================== | 78% 313 MB
|============================================================================================== | 78% 313 MB
|============================================================================================== | 78% 313 MB
|============================================================================================== | 78% 314 MB
|============================================================================================== | 78% 314 MB
|============================================================================================== | 78% 315 MB
|============================================================================================== | 79% 315 MB
|=============================================================================================== | 79% 315 MB
|=============================================================================================== | 79% 316 MB
|=============================================================================================== | 79% 316 MB
|=============================================================================================== | 79% 317 MB
|=============================================================================================== | 79% 317 MB
|=============================================================================================== | 79% 317 MB
|=============================================================================================== | 79% 318 MB
|=============================================================================================== | 79% 318 MB
|=============================================================================================== | 79% 319 MB
|================================================================================================ | 80% 319 MB
|================================================================================================ | 80% 319 MB
|================================================================================================ | 80% 320 MB
|================================================================================================ | 80% 320 MB
|================================================================================================ | 80% 320 MB
|================================================================================================ | 80% 321 MB
|================================================================================================ | 80% 321 MB
|================================================================================================ | 80% 322 MB
|================================================================================================= | 80% 322 MB
|================================================================================================= | 80% 322 MB
|================================================================================================= | 81% 323 MB
|================================================================================================= | 81% 323 MB
|================================================================================================= | 81% 324 MB
|================================================================================================= | 81% 324 MB
|================================================================================================= | 81% 324 MB
|================================================================================================= | 81% 325 MB
|================================================================================================= | 81% 325 MB
|================================================================================================== | 81% 326 MB
|================================================================================================== | 81% 326 MB
|================================================================================================== | 81% 326 MB
|================================================================================================== | 82% 327 MB
|================================================================================================== | 82% 327 MB
|================================================================================================== | 82% 328 MB
|================================================================================================== | 82% 328 MB
|================================================================================================== | 82% 328 MB
|=================================================================================================== | 82% 329 MB
|=================================================================================================== | 82% 329 MB
|=================================================================================================== | 82% 330 MB
|=================================================================================================== | 82% 330 MB
|=================================================================================================== | 82% 330 MB
|=================================================================================================== | 83% 331 MB
|=================================================================================================== | 83% 331 MB
|=================================================================================================== | 83% 332 MB
|=================================================================================================== | 83% 332 MB
|==================================================================================================== | 83% 332 MB
|==================================================================================================== | 83% 333 MB
|==================================================================================================== | 83% 333 MB
|==================================================================================================== | 83% 333 MB
|==================================================================================================== | 83% 334 MB
|==================================================================================================== | 83% 334 MB
|==================================================================================================== | 83% 335 MB
|==================================================================================================== | 84% 335 MB
|===================================================================================================== | 84% 335 MB
|===================================================================================================== | 84% 336 MB
|===================================================================================================== | 84% 336 MB
|===================================================================================================== | 84% 337 MB
|===================================================================================================== | 84% 337 MB
|===================================================================================================== | 84% 337 MB
|===================================================================================================== | 84% 338 MB
|===================================================================================================== | 84% 338 MB
|===================================================================================================== | 84% 339 MB
|====================================================================================================== | 85% 339 MB
|====================================================================================================== | 85% 339 MB
|====================================================================================================== | 85% 340 MB
|====================================================================================================== | 85% 340 MB
|====================================================================================================== | 85% 341 MB
|====================================================================================================== | 85% 341 MB
|====================================================================================================== | 85% 341 MB
|====================================================================================================== | 85% 342 MB
|======================================================================================================= | 85% 342 MB
|======================================================================================================= | 85% 343 MB
|======================================================================================================= | 86% 343 MB
|======================================================================================================= | 86% 343 MB
|======================================================================================================= | 86% 344 MB
|======================================================================================================= | 86% 344 MB
|======================================================================================================= | 86% 345 MB
|======================================================================================================= | 86% 345 MB
|======================================================================================================== | 86% 345 MB
|======================================================================================================== | 86% 346 MB
|======================================================================================================== | 86% 346 MB
|======================================================================================================== | 86% 346 MB
|======================================================================================================== | 87% 347 MB
|======================================================================================================== | 87% 347 MB
|======================================================================================================== | 87% 348 MB
|======================================================================================================== | 87% 348 MB
|======================================================================================================== | 87% 348 MB
|========================================================================================================= | 87% 349 MB
|========================================================================================================= | 87% 349 MB
|========================================================================================================= | 87% 349 MB
|========================================================================================================= | 87% 350 MB
|========================================================================================================= | 87% 350 MB
|========================================================================================================= | 88% 351 MB
|========================================================================================================= | 88% 351 MB
|========================================================================================================= | 88% 351 MB
|========================================================================================================= | 88% 352 MB
|========================================================================================================== | 88% 352 MB
|========================================================================================================== | 88% 352 MB
|========================================================================================================== | 88% 353 MB
|========================================================================================================== | 88% 353 MB
|========================================================================================================== | 88% 354 MB
|========================================================================================================== | 88% 354 MB
|========================================================================================================== | 88% 354 MB
|========================================================================================================== | 89% 355 MB
|========================================================================================================== | 89% 355 MB
|=========================================================================================================== | 89% 355 MB
|=========================================================================================================== | 89% 356 MB
|=========================================================================================================== | 89% 356 MB
|=========================================================================================================== | 89% 357 MB
|=========================================================================================================== | 89% 357 MB
|=========================================================================================================== | 89% 357 MB
|=========================================================================================================== | 89% 358 MB
|=========================================================================================================== | 89% 358 MB
|=========================================================================================================== | 89% 358 MB
|============================================================================================================ | 90% 359 MB
|============================================================================================================ | 90% 359 MB
|============================================================================================================ | 90% 359 MB
|============================================================================================================ | 90% 360 MB
|============================================================================================================ | 90% 360 MB
|============================================================================================================ | 90% 360 MB
|============================================================================================================ | 90% 361 MB
|============================================================================================================ | 90% 361 MB
|============================================================================================================ | 90% 362 MB
|============================================================================================================= | 90% 362 MB
|============================================================================================================= | 90% 362 MB
|============================================================================================================= | 91% 363 MB
|============================================================================================================= | 91% 363 MB
|============================================================================================================= | 91% 364 MB
|============================================================================================================= | 91% 364 MB
|============================================================================================================= | 91% 364 MB
|============================================================================================================= | 91% 365 MB
|============================================================================================================= | 91% 365 MB
|============================================================================================================== | 91% 366 MB
|============================================================================================================== | 91% 366 MB
|============================================================================================================== | 91% 366 MB
|============================================================================================================== | 92% 367 MB
|============================================================================================================== | 92% 367 MB
|============================================================================================================== | 92% 367 MB
|============================================================================================================== | 92% 368 MB
|============================================================================================================== | 92% 368 MB
|=============================================================================================================== | 92% 369 MB
|=============================================================================================================== | 92% 369 MB
|=============================================================================================================== | 92% 369 MB
|=============================================================================================================== | 92% 370 MB
|=============================================================================================================== | 92% 370 MB
|=============================================================================================================== | 92% 370 MB
|=============================================================================================================== | 93% 371 MB
|=============================================================================================================== | 93% 371 MB
|=============================================================================================================== | 93% 372 MB
|================================================================================================================ | 93% 372 MB
|================================================================================================================ | 93% 372 MB
|================================================================================================================ | 93% 373 MB
|================================================================================================================ | 93% 373 MB
|================================================================================================================ | 93% 373 MB
|================================================================================================================ | 93% 374 MB
|================================================================================================================ | 93% 374 MB
|================================================================================================================ | 93% 374 MB
|================================================================================================================ | 94% 375 MB
|================================================================================================================ | 94% 375 MB
|================================================================================================================= | 94% 375 MB
|================================================================================================================= | 94% 376 MB
|================================================================================================================= | 94% 376 MB
|================================================================================================================= | 94% 377 MB
|================================================================================================================= | 94% 377 MB
|================================================================================================================= | 94% 377 MB
|================================================================================================================= | 94% 378 MB
|================================================================================================================= | 94% 378 MB
|================================================================================================================= | 94% 378 MB
|================================================================================================================== | 95% 379 MB
|================================================================================================================== | 95% 379 MB
|================================================================================================================== | 95% 379 MB
|================================================================================================================== | 95% 380 MB
|================================================================================================================== | 95% 380 MB
|================================================================================================================== | 95% 380 MB
|================================================================================================================== | 95% 381 MB
|================================================================================================================== | 95% 381 MB
|================================================================================================================== | 95% 382 MB
|=================================================================================================================== | 95% 382 MB
|=================================================================================================================== | 95% 382 MB
|=================================================================================================================== | 95% 383 MB
|=================================================================================================================== | 96% 383 MB
|=================================================================================================================== | 96% 383 MB
|=================================================================================================================== | 96% 384 MB
|=================================================================================================================== | 96% 384 MB
|=================================================================================================================== | 96% 384 MB
|=================================================================================================================== | 96% 385 MB
|=================================================================================================================== | 96% 385 MB
|==================================================================================================================== | 96% 385 MB
|==================================================================================================================== | 96% 386 MB
|==================================================================================================================== | 96% 386 MB
|==================================================================================================================== | 96% 386 MB
|==================================================================================================================== | 97% 387 MB
|==================================================================================================================== | 97% 387 MB
|==================================================================================================================== | 97% 387 MB
|==================================================================================================================== | 97% 388 MB
|==================================================================================================================== | 97% 388 MB
|==================================================================================================================== | 97% 388 MB
|===================================================================================================================== | 97% 389 MB
|===================================================================================================================== | 97% 389 MB
|===================================================================================================================== | 97% 389 MB
|===================================================================================================================== | 97% 390 MB
|===================================================================================================================== | 97% 390 MB
|===================================================================================================================== | 97% 390 MB
|===================================================================================================================== | 98% 391 MB
|===================================================================================================================== | 98% 391 MB
|===================================================================================================================== | 98% 391 MB
|===================================================================================================================== | 98% 392 MB
|====================================================================================================================== | 98% 392 MB
|====================================================================================================================== | 98% 392 MB
|====================================================================================================================== | 98% 393 MB
|====================================================================================================================== | 98% 393 MB
|====================================================================================================================== | 98% 393 MB
|====================================================================================================================== | 98% 394 MB
|====================================================================================================================== | 98% 394 MB
|====================================================================================================================== | 98% 394 MB
|====================================================================================================================== | 99% 395 MB
|====================================================================================================================== | 99% 395 MB
|=======================================================================================================================| 99% 395 MB
|=======================================================================================================================| 99% 396 MB
|=======================================================================================================================| 99% 396 MB
|=======================================================================================================================| 99% 396 MB
|=======================================================================================================================| 99% 397 MB
|=======================================================================================================================| 99% 397 MB
|=======================================================================================================================| 99% 397 MB
|=======================================================================================================================| 99% 398 MB
|=======================================================================================================================| 99% 398 MB
|=======================================================================================================================| 99% 398 MB
|========================================================================================================================| 100% 398 MB
snps
filter to keep snps where there is data from all samples
snps <- snps %>%
filter({select(., matches("[0-9]")) %>% complete.cases() })
snps
snps <- snps %>%
mutate(TOTAL_DEPTH= {str_extract(INFO, "DP=[0-9]*") %>%
str_remove("DP=") %>%
as.numeric() }
) %>%
filter(QUAL >=100,
nchar(ALT)==1,
TOTAL_DEPTH > quantile(TOTAL_DEPTH, 0.05),
TOTAL_DEPTH < quantile(TOTAL_DEPTH, 0.95))
snps
unpack the information differnet samples:
samples <- colnames(snps) %>% str_subset("^[0-9]")
for (s in samples) {
snps <- snps %>%
separate(!!s, into=paste(s,c("gt","tot.depth","allele.depth","ref.depth","ref.qual","alt.depth","alt.qual","gt.lik"),sep="_"),
sep=":", convert = TRUE)
}
snps
For the PCA we only need the genotype info
gts <- snps %>%
select(CHROM, POS, ends_with("_gt"))
gts
remove the 38LTR gample
gts <- gts %>% select(-`38LTR_gt`)
convert this to numeric
geno.numeric <- gts %>%
select(-CHROM, -POS) %>%
lapply(factor) %>% # convert charcters to "factors", where each category is internally represented as a number
as.data.frame() %>% # reformat
data.matrix() %>%# convert to numeric
t()
colnames(geno.numeric) <- str_c(gts$CHROM, "_", gts$POS)
head(geno.numeric[,1:5],10)
GCZN01000007.1_2815 GCZN01000007.1_2834 GCZN01000007.1_2865 GCZN01000007.1_2881 GCZN01000007.1_2970
X42LTR_gt 2 3 2 2 2
X42LTRR_gt 2 2 2 2 1
X43LTR_gt 2 2 2 2 2
X43LTRR_gt 2 2 2 2 2
X49LTWR_gt 2 2 2 2 2
X49LTWRR_gt 3 3 3 3 1
X95LTWR_gt 2 3 3 2 2
X95LTWRR_gt 2 3 3 2 2
X99LTWR_gt 2 2 2 2 2
dim(geno.numeric)
[1] 9 134421
dim(gts)
[1] 134421 11
get the principal components
pca <- prcomp(geno.numeric)
summary(pca)
Importance of components:
PC1 PC2 PC3 PC4 PC5 PC6 PC7 PC8 PC9
Standard deviation 78.9711 75.4129 60.8894 54.9581 52.3780 45.30719 43.88667 42.97555 1.288e-11
Proportion of Variance 0.2291 0.2089 0.1362 0.1110 0.1008 0.07541 0.07076 0.06785 0.000e+00
Cumulative Proportion 0.2291 0.4380 0.5742 0.6852 0.7860 0.86139 0.93215 1.00000 1.000e+00
plot it
plot.data <- pca$x %>%
as.data.frame %>%
rownames_to_column("sample") %>%
mutate(response=str_extract(sample, "(LTR|LTWR)")) %>%
gather(key="component", value="value",PC2:PC9)
plots <- map(sort(unique(plot.data$component)), function(x) {
plot.data %>%
filter(component==x) %>%
ggplot(aes(x=PC1, y= value, label=sample, color=response)) +
geom_point() + ylab(x)
}
)
plots
[[1]]
[[2]]
[[3]]
[[4]]
[[5]]
[[6]]
[[7]]
[[8]]
loadings <- as.data.frame(pca$rotation) %>%
rownames_to_column("snp") %>%
select(PC1, snp) %>%
arrange(desc(abs(PC1)))
loadings
contributions <- loadings %>%
separate(snp, into=c("contig", "pos"), sep="_") %>%
group_by(contig) %>%
summarize(abs.contribution = abs(sum(PC1)),
contribution = sum(PC1),
number_of_snps = n()) %>%
arrange(desc(abs.contribution))
contributions
bring in seq lineghts
lengths <- read_csv("../input/Pinsaporeference1_lengths.csv", col_names = c("contig", "length"), skip=1) %>%
mutate(contig = str_remove(contig, " .*"))
Parsed with column specification:
cols(
contig = col_character(),
length = col_integer()
)
lengths
contributions <- contributions %>%
left_join(lengths) %>%
mutate(snps_per_100bp = round(number_of_snps / length * 100, 2)) %>%
select(contig, contribution, length, number_of_snps, snps_per_100bp)
Joining, by = "contig"
contributions
write_csv(contributions, "../output/gene_contributions.csv.gz")
pc1pc2 <- pca$x %>%
as.data.frame() %>%
rownames_to_column("ID") %>%
select(ID, PC1, PC2) %>%
mutate(ID={str_replace(ID, "W", "N") %>%
str_replace("RR", "R2") %>%
str_remove_all("(X|_gt)") },
response=ifelse(str_detect(ID,"N"), "no recovery", "recovery"))
pc1pc2
pc1pc2 %>%
ggplot(aes(x=PC1, y = PC2, label=ID, color=response)) +
geom_point() +
geom_text_repel(show.legend=FALSE, direction="y")
ggsave("../output/PCA.pdf")
Saving 7.29 x 4.51 in image